© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21559
    Prev
    Next
    INDEX
    Explanations

    versatile adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åįijå¾®
    -0.07
    为äºĨå®ŀçİ°
    -0.07
    æĶ¯éħį
    -0.07
    å¹¼å°ı
    -0.07
    chemas
    -0.07
    çī¹æ®ĬæĢ§
    -0.07
    oping
    -0.06
     ÙħعÙĬÙĨ
    -0.06
     Certain
    -0.06
    ABCDEFG
    -0.06
    POSITIVE LOGITS
    ä¼ĺçĤ¹æĺ¯
    0.12
    缺çĤ¹æĺ¯
    0.11
    å¹¿æ³ĽçĶ¨äºİ
    0.09
    çļĦä¼ĺçĤ¹
    0.09
    éĿŀ常éĢĤåIJĪ
    0.09
    éĢĤçĶ¨äºİ
    0.09
    æĹ¢èĥ½
    0.09
    å¾ĪéĢĤåIJĪ
    0.09
     versatile
    0.09
    oriously
    0.09
    Activations Density 0.072%

    No Known Activations